Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Validate design system compliance in code and detect token usage violations
.claude/skills/a5c-ai-design-system-validator/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-18 | ✗→✓ | ▲ Improved | 212% | 0% |
| case-01 | ✗→✓ | ▲ Improved | 1009% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -22% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -87% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -38% | 0% |
Validate that code adheres to design system specifications, checking token usage, component props, and style consistency.
json{ "type": "object", "properties": { "scanPath": { "type": "string", "description": "Path to code to validate" }, "tokenDefinitions": { "type": "string", "description": "Path to design token definitions" }, "rules": { "type": "object", "properties": { "enforceTokenColors": { "type": "boolean", "default": true }, "enforceTokenSpacing": { "type": "boolean", "default": true }, "enforceTokenTypography": { "type": "boolean", "default": true }, "allowHardcodedValues": { "type": "array", "items": { "type": "string" } } } }, "fileTypes": { "type": "array", "items": { "type": "string" }, "default": ["css", "scss", "tsx", "jsx"] }, "severity": { "type": "string", "enum": ["error", "warning", "info"], "default": "warning" } }, "required": ["scanPath", "tokenDefinitions"] }
json{ "type": "object", "properties": { "violations": { "type": "array", "items": { "type": "object", "properties": { "file": { "type": "string" }, "line": { "type": "number" }, "rule": { "type": "string" }, "message": { "type": "string" }, "suggestion": { "type": "string" } } } }, "summary": { "type": "object", "properties": { "filesScanned": { "type": "number" }, "totalViolations": { "type": "number" }, "byRule": { "type": "object" }, "complianceScore": { "type": "number" } } }, "tokenCoverage": { "type": "object", "description": "Token usage statistics" } } }
javascriptconst result = await skill.execute({ scanPath: './src/components', tokenDefinitions: './tokens/design-tokens.json', rules: { enforceTokenColors: true, enforceTokenSpacing: true, enforceTokenTypography: true }, severity: 'warning' });
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-04 | pass→pass | 12,268 | 8,100 | -34% | 1 | 1 | 0% | 1,273 | 1,295 | +2% | 0 | 0 | — |
case-18 | fail→pass | 8,300 | 7,001 | -16% | 1 | 1 | 0% | 328 | 1,022 | +212% | 0 | 0 | — |
case-01 | fail→pass | 14,990 | 18,379 | +23% | 1 | 1 | 0% | 346 | 3,837 | +1009% | 0 | 0 | — |
case-02 | fail→fail | 40,929 | 26,161 | -36% | 1 | 1 | 0% | 8,267 | 5,610 | -32% | 0 | 0 | — |
case-03 | fail→fail | 26,893 | 19,074 | -29% | 1 | 1 | 0% | 4,373 | 3,719 | -15% | 0 | 0 | — |
case-05 | fail→pass | 13,108 | 6,807 | -48% | 1 | 1 | 0% | 1,278 | 998 | -22% | 0 | 0 | — |
case-06 | fail→pass | 45,827 | 6,939 | -85% | 1 | 1 | 0% | 8,219 | 1,035 | -87% | 0 | 0 | — |
case-07 | fail→pass | 15,636 | 8,262 | -47% | 1 | 1 | 0% | 1,842 | 1,141 | -38% | 0 | 0 | — |
case-08 | fail→pass | 14,347 | 7,392 | -48% | 1 | 1 | 0% | 1,653 | 1,178 | -29% | 0 | 0 | — |
case-09 | fail→pass | 17,970 | 6,695 | -63% | 1 | 1 | 0% | 2,223 | 981 | -56% | 0 | 0 | — |
case-10 | fail→pass | 34,602 | 6,750 | -80% | 1 | 1 | 0% | 5,154 | 1,042 | -80% | 0 | 0 | — |
case-11 | fail→pass | 13,831 | 7,281 | -47% | 1 | 1 | 0% | 1,748 | 1,170 | -33% | 0 | 0 | — |
case-12 | fail→pass | 10,082 | 6,857 | -32% | 1 | 1 | 0% | 684 | 966 | +41% | 0 | 0 | — |
case-13 | fail→pass | 37,147 | 6,865 | -82% | 1 | 1 | 0% | 3,570 | 1,013 | -72% | 0 | 0 | — |
case-14 | fail→fail | 25,651 | 9,014 | -65% | 1 | 1 | 0% | 1,107 | 1,506 | +36% | 0 | 0 | — |
case-15 | pass→pass | 19,697 | 32,499 | +65% | 1 | 1 | 0% | 3,912 | 4,177 | +7% | 0 | 0 | — |
case-16 | pass→pass | 15,986 | 14,730 | -8% | 1 | 1 | 0% | 1,865 | 2,599 | +39% | 0 | 0 | — |
case-17 | pass→pass | 24,103 | 29,626 | +23% | 1 | 1 | 0% | 4,500 | 5,806 | +29% | 0 | 0 | — |
case-19 | pass→pass | 7,648 | 9,048 | +18% | 1 | 1 | 0% | 1,220 | 1,434 | +18% | 0 | 0 | — |
case-20 | pass→pass | 12,766 | 7,526 | -41% | 1 | 1 | 0% | 1,233 | 1,269 | +3% | 0 | 0 | — |
case-21 | pass→pass | 29,488 | 2,366 | -92% | 1 | 1 | 0% | 3,972 | 1,190 | -70% | 0 | 0 | — |
case-22 | fail→pass | 2,561 | 2,180 | -15% | 1 | 1 | 0% | 211 | 1,039 | +392% | 0 | 0 | — |
case-23 | pass→pass | 13,820 | 4,072 | -71% | 1 | 1 | 0% | 1,756 | 1,063 | -39% | 0 | 0 | — |
case-24 | fail→pass | 19,286 | 2,123 | -89% | 1 | 1 | 0% | 2,231 | 1,053 | -53% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 24 cases were attempted, and 23 counted toward the lift figure. The other 1 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +54 percentage points is the difference between those two pass rates over the 23 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.